Shuffled Patch-Wise Supervision for Presentation Attack Detection

Alperen Kantarci, Hasan Dertli, Hazim Kemal Ekenel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Face anti-spoofing is essential to prevent false facial verification by using a photo, video, mask, or a different substitute for an authorized person's face. Most of the state-of-the-art presentation attack detection (PAD) systems suffer from overfitting, where they achieve near-perfect scores on a single dataset but fail on a different dataset with more realistic data. This problem drives researchers to develop models that perform well under real-world conditions. This is an especially challenging problem for frame-based presentation attack detection systems that use convolutional neural networks (CNN). To this end, we propose a new PAD approach, which combines pixel-wise binary supervision with patch-based CNN. We believe that training a CNN with face patches allows the model to distinguish spoofs without learning background or dataset-specific traces. We tested the proposed method both on the standard benchmark datasets - Replay-Mobile, OULU-NPU - and on a real-world dataset. The proposed approach shows its superiority on challenging experimental setups.

Original languageEnglish (US)
Title of host publicationBIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group
EditorsArslan Bromme, Christoph Busch, Naser Damer, Antitza Dantcheva, Marta Gomez-Barrero, Kiran Raja, Christian Rathgeb, Ana F. Sequeira, Andreas Uhl
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9783885797098
DOIs
StatePublished - Sep 2021
Event20th International Conference of the Biometrics Special Interest Group, BIOSIG 2021 - Darmstadt, Germany
Duration: Sep 15 2021Sep 17 2021

Publication series

NameBIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group

Conference

Conference20th International Conference of the Biometrics Special Interest Group, BIOSIG 2021
Country/TerritoryGermany
CityDarmstadt
Period9/15/219/17/21

Keywords

  • convolutional neural networks
  • Face antispoofing
  • presentation attack detection
  • real-world dataset

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Shuffled Patch-Wise Supervision for Presentation Attack Detection'. Together they form a unique fingerprint.

Cite this